{"id":"https://openalex.org/W3197584784","doi":"https://doi.org/10.21437/interspeech.2021-2041","title":"Look Who’s Talking: Active Speaker Detection in the Wild","display_name":"Look Who’s Talking: Active Speaker Detection in the Wild","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197584784","doi":"https://doi.org/10.21437/interspeech.2021-2041","mag":"3197584784"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2041","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022133103","display_name":"You Jin Kim","orcid":"https://orcid.org/0000-0002-4952-5532"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"You Jin Kim","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hee-Soo Heo","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022555543","display_name":"Soyeon Choe","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyeon Choe","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046276512","display_name":"Soo-Whan Chung","orcid":"https://orcid.org/0000-0001-6529-2196"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Whan Chung","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019238472","display_name":"Yoohwan Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoohwan Kwon","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086369397","display_name":"Bong\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-7896-2961"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bong-Jin Lee","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067505925","display_name":"Youngki Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngki Kwon","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5022133103"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":2.1515,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88263763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3675","last_page":"3679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.564516544342041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49566400051116943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.564516544342041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49566400051116943}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2041","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W9038322","https://openalex.org/W2038010270","https://openalex.org/W2076462394","https://openalex.org/W2115175902","https://openalex.org/W2157331557","https://openalex.org/W2316138215","https://openalex.org/W2339852062","https://openalex.org/W2519224033","https://openalex.org/W2597757402","https://openalex.org/W2604379605","https://openalex.org/W2621109248","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2912581782","https://openalex.org/W2916104401","https://openalex.org/W2938358845","https://openalex.org/W2942265585","https://openalex.org/W2950864153","https://openalex.org/W2952746495","https://openalex.org/W2954458766","https://openalex.org/W2963082324","https://openalex.org/W2963307811","https://openalex.org/W2963524571","https://openalex.org/W2964171275","https://openalex.org/W2972729214","https://openalex.org/W2981087920","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3015841457","https://openalex.org/W3016098309","https://openalex.org/W3023351797","https://openalex.org/W3024147341","https://openalex.org/W3038871978","https://openalex.org/W3173382920","https://openalex.org/W4307196995"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"a":[5,37,125,130,134],"novel":[6],"audio-visual":[7,43],"dataset":[8,49,71,99,142],"for":[9,41],"active":[10,19,33,59,114],"speaker":[11,16,34,60,97],"detection":[12,35],"in":[13,67,104,124,153,163],"the":[14,28,56,64,68,105,111,120,141,145,157,164],"wild.A":[15],"is":[17,25,30,36,46,151],"considered":[18],"when":[20],"his":[21],"or":[22],"her":[23],"face":[24],"visible":[26],"and":[27,75,84,91,113,133],"voice":[29],"audible":[31,87],"simultaneously.Although":[32],"crucial":[38],"pre-processing":[39],"step":[40],"many":[42],"tasks,":[44],"there":[45],"no":[47],"existing":[48,96],"of":[50,58,86,102,122,148,160],"natural":[51],"human":[52],"speech":[53,77,81],"to":[54,143,155],"evaluate":[55],"performance":[57],"detection.We":[61],"therefore":[62],"curate":[63],"Active":[65],"Speakers":[66],"Wild":[69],"(ASW)":[70],"which":[72],"contains":[73],"videos":[74,103,112,162],"co-occurring":[76],"segments":[78,88,115],"with":[79],"dense":[80],"activity":[82],"labels.Videos":[83],"timestamps":[85,121],"are":[89,108,116,138],"parsed":[90],"adopted":[92],"from":[93,110],"VoxConverse,":[94],"an":[95],"diarisation":[98],"that":[100],"consists":[101],"wild.Face":[106],"tracks":[107],"extracted":[109],"annotated":[117],"based":[118],"on":[119,140],"VoxConverse":[123],"semi-automatic":[126],"way.Two":[127],"reference":[128],"systems,":[129],"self-supervised":[131],"system":[132],"fully":[135],"supervised":[136],"one,":[137],"evaluated":[139],"provide":[144],"baseline":[146],"performances":[147],"ASW.Cross-domain":[149],"evaluation":[150],"conducted":[152],"order":[154],"show":[156],"negative":[158],"effect":[159],"dubbed":[161],"training":[165],"data.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}